LLM Watermarking

LLM: Large Language Model

Overview

Large language model watermarking studies how to mark generated text, model behavior, or model parameters so that provenance, ownership, or use of protected data can later be checked. Common approaches add keyed statistical patterns to token sampling, encode messages with error-correcting codes, or place signals in semantic structure, model weights, activations, and agent actions. Researchers evaluate detection and message recovery alongside text quality, false-positive rates, and resistance to paraphrasing, translation, editing, fine-tuning, and other attacks. The central tension is making marks reliable and hard to forge or remove without harming usefulness, while ensuring detection remains trustworthy at real-world scale.

Latest papers

122 papers14 papers in the last four weeks, down 42% on the four weeks before. 0.1% of all new papers.

May 27, 2025

The Feasibility of Topic-Based Watermarking on Academic Peer Reviews

Large language models (LLMs) are increasingly integrated into academic workflows, with many conferences and journals permitting their use for tasks such as language refinement and literature summarization. However, their use in peer review remains prohibited due to concerns around confidentiality breaches, hallucinated content, and inconsistent evaluations. As LLM-generated text becomes more indistinguishable from human writing, there is a growing need for reliable attribution mechanisms to preserve the integrity of the review process. In this work, we evaluate topic-based watermarking (TBW), a semantic-aware technique designed to embed detectable signals into LLM-generated text. We conduct a systematic assessment across multiple LLM configurations, including base, few-shot, and fine-tuned variants, using authentic peer review data from academic conferences. Our results show that TBW maintains review quality relative to non-watermarked outputs, while demonstrating robust detection performance under paraphrasing. These findings highlight the viability of TBW as a minimally intrusive and practical solution for LLM attribution in peer review settings.
Dec 28, 2023

Optimizing watermarks for large language models

With the rise of large language models (LLMs) and concerns about potential misuse, watermarks for generative LLMs have recently attracted much attention. An important aspect of such watermarks is the trade-off between their identifiability and their impact on the quality of the generated text. This paper introduces a systematic approach to this trade-off in terms of a multi-objective optimization problem. For a large class of robust, efficient watermarks, the associated Pareto optimal solutions are identified and shown to outperform the currently default watermark.